Skip to main content
SpringerLink
Log in

A Hyperparameters automatic optimization method of time graph convolution network model for traffic prediction

  • Published:
Wireless Networks Aims and scope Submit manuscript

Abstract

Smart transportation is an essential component of the smart city. Traffic prediction is an important issue in smart transportation. The convolutional neural networks (GCN) are an effective approach for traffic prediction. However, the GCN meets some challenges, such as stability of prediction precision and computation cost, in traffic prediction. The hyperparameters significantly affect the performance of GCN. We conduct a regression analysis between hyperparameters and GCN performance. Our simulation results show that there is the obvious optimal point of hyperparameters. Some empirical suggestion is given to adjust the hyperparameters based on the simulation results.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Zhang, K., Chen, L., An, Y., et al. (2019). A QoE test system for vehicular voice cloud services. Mobile Networks and Applications. https://doi.org/10.1007/s11036-019-01415-3

    Article  Google Scholar 

  2. Jiang, D., Wang, Z., Huo, L., et al. (2020). A performance measurement and analysis method for software-defined networking of IoV. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/TITS.2020.3029076

    Article  Google Scholar 

  3. Huo, L., Jiang, D., Lv, Z., et al. (2020). An intelligent optimization-based traffic information acquirement approach to software-defined networking. Computational Intelligence, 36(1), 151–171.

  4. Chen, L., Jiang, D., Bao, R., Xiong, J., Liu, F., & Bei, L. (2017). MIMO Scheduling effectiveness analysis for bursty data service from view of QoE. Chinese Journal of Electronics, 26(5), 1079–1085.

    Article  Google Scholar 

  5. Jiang, D., Wang, Y., Lv, Z., et al. (2020). Big data analysis-based network behavior insight of cellular networks for industry 4.0 applications. IEEE Transactions on Industrial Informatics, 16(2), 1310–1320.

    Article  Google Scholar 

  6. Jiang, D., Huo, L., & Song, H. (2018). Rethinking behaviors and activities of base stations in mobile cellular networks based on big data analysis. IEEE Transactions on Network Science and Engineering, 1(1), 1–12.

    MathSciNet  Google Scholar 

  7. Chen, L., Jiang, D., Song, H., Wang, P., Bao, R., Zhang, K., & Li, Y. (2018). A lightweight end-side user experience data collection system for quality evaluation of multimedia communications. IEEE Access, 6(1), 15408–15419.

    Article  Google Scholar 

  8. Chen, L., & Zhang, L. (2020). Spectral efficiency analysis for massive MIMO system under QoS constraint: An effective capacity perspective. Mobile Networks and Applications. https://doi.org/10.1007/s11036-019-01414-4

    Article  Google Scholar 

  9. Wang, F., Jiang, D., Qi, S., et al. (2021). A dynamic resource scheduling scheme in edge computing satellite networks. Mobile Networks and Applications, 26, 597–608.

    Article  Google Scholar 

  10. Jiang, D., Huo, L., Lv, Z., et al. (2018). A joint multi-criteria utility-based network selection approach for vehicle-to-infrastructure networking. IEEE Transactions on Intelligent Transportation Systems, 19(10), 3305–3319.

    Article  Google Scholar 

  11. Jiang, D., Zhang, P., Lv, Z., et al. (2016). Energy-efficient multi-constraint routing algorithm with load balancing for smart city applications. IEEE Internet of Things Journal, 3(6), 1437–1447.

    Article  Google Scholar 

  12. Jiang, D., Huo, L., Zhang, P., et al. (2020). Energy-efficient heterogeneous networking for electric vehicles networks in smart future cities. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/TITS.2020.3029015

    Article  Google Scholar 

  13. Wang, Z., Jiang, D., Zhang, Z., et al. (2021). A polymorphic heterogeneous security architecture for edge-enabled smart grid. Sustainable Cities and Society, 67(4), 1–16. https://doi.org/10.1016/j.scs.2020.102661

    Article  Google Scholar 

  14. Jiang, D., Wang, W., Shi, L., et al. (2018). A compressive sensing-based approach to end-to-end network traffic reconstruction. IEEE Transactions on Network Science and Engineering, 5(3), 1–12.

    Google Scholar 

  15. Jiang, D., Huo, L., & Li, Y. (2018). Fine-granularity inference and estimations to network traffic for SDN. PLoS ONE, 13(5), 1–23.

    Google Scholar 

  16. Jiang, D., Wang, F., Lv, Z., et al. (2021). QoE-Aware efficient content distribution scheme for satellite-terrestrial networks. IEEE Transactions on Mobile Computing. https://doi.org/10.1109/TMC.2021.3074917

    Article  Google Scholar 

  17. Jiang, D., Wang, Z., Wang, W., et al. (2021). AI-assisted energy-efficient and intelligent routing for reconfigurable wireless networks. IEEE Transactions on Network Science and Engineering. https://doi.org/10.1109/TNSE.2021.3075428

    Article  Google Scholar 

  18. Huo, L., Jiang, D., Qi, S., et al. (2021). An AI-based adaptive cognitive modeling and measurement method of network traffic for EIS. Mobile Networks and Applications, 26, 575–585.

    Article  Google Scholar 

  19. Huo, L., Jiang, D., Zhu, X., et al. (2019). An SDN-based fine-grained measurement and modeling approach to vehicular communication network traffic. International Journal of Communication Systems. https://doi.org/10.1002/dac.4092.

  20. Silver, D., et al. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484–489.

    Article  Google Scholar 

  21. Silver, D., et al. (2017). Mastering the game of go without human knowledge. Nature, 550(7676), 354–359.

    Article  Google Scholar 

  22. Moravˇcik, M., Schmid, M., Burch, N., Lisý, V., Morrill, D., Bard, N., Davis, T., Waugh, K., Johanson, M., & Bowling, M. (2017). DeepStack: Expert-level artifificial intelligence in heads-up no-limit poker. Science, 356(6337), 508–513.

    Article  MathSciNet  MATH  Google Scholar 

  23. Park, D., & Rilett, L. R. (1999). Forecasting freeway link travel times with a multilayer feedforward neural network. Computer-Aided Civil and Infrastructure Engineering, 14(5), 357–367.

    Article  Google Scholar 

  24. Huang, W., Song, G., Hong, H., & Xie, K. (2014). Deep architecture for traffic flow prediction: Deep belief networks with multitask learning. IEEE Transactions on Intelligent Transportation Systems, 15(5), 2191–2201.

    Article  Google Scholar 

  25. Fu, R., Zhang, Z., & Li, L. (2016). Using LSTM and GRU neural network methods for traffic flow prediction. In Proceedings of 31st youth academic annual conference of Chinese association of automation (YAC) (pp. 324–328). Wuhan, China.

  26. Van Lint, J. W. C., Hoogendoorn, S. P., & van Zuylen, H. J. (2002). Freeway travel time prediction with state-space neural networks: Modeling statespace dynamics with recurrent neural networks. Transportation Research Record, 1811(1), 30–39.

    Article  MATH  Google Scholar 

  27. Zhao, L., Song, Y., Zhang, C., et al. (2018). T-GCN: A temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems. https://doi.org/10.1109/TITS.2019.2935152

  28. Ye, F., & Tang, H. (2019). Skeleton-based action recognition with JRR-GCN. Electronics Letters, 55(17), 933–935.

    Article  Google Scholar 

  29. Ding, L., Huang, Z., & Chen, G. (2019). An FPGA implementation of GCN with sparse adjacency matrix. In 2019 IEEE 13th international conference on ASIC (ASICON).

  30. Zheng, J., & Li, D. (2019). GCN-TC: combining trace graph with statistical features for network traffic classification. In 2019 IEEE International Conference on Communications (ICC).

  31. Li, Z., Xiong, G., & Chen, Y. (2019). A hybrid deep learning approach with GCN and LSTM for traffific flow prediction*. In 2019 IEEE intelligent transportation systems conference (ITSC).

  32. Reddi, S. J., Kale, S., & Kumar, S. (2019). On the convergence of adam and beyond. arXiv:1904.09237.

  33. Keskar, N. S., Socher, R. (2017). Improving Generalization Performance by Switching from Adam to SGD. arXiv:1712.07628.

  34. Hoffer, E., Hubara, I., & Soudry, D. (2017). Train longer, generalize better: closing the generalization gap in large batch training of neural networks. In Advances in neural information processing systems (pp. 1731–1741).

  35. Goyal, P., Dollar, P., Girshick, R.B., et al. (2017). Accurate, large minibatch SGD: training ImageNet in 1 Hour. arXiv: Computer vision and pattern recognition.

  36. Keskar, N. S., & Socher, R. (2017). Improving generalization performance by switching from adam to SGD. arXiv preprint arXiv:1712.07628.

  37. Reddi, S. J., Kale, S., & Kumar, S. (2018). On the convergence of adam and beyond.

  38. Smith, L. N. (2017). Cyclical learning rates for training neural networks. In 2017 IEEE winter conference on applications of computer vision (WACV). IEEE (pp. 464–472).

  39. Smith, S. L., Kindermans, P. J., Ying, C., et al. (2017). Don't decay the learning rate, increase the batch size. arXiv preprint arXiv:1711.00489.

  40. Cardona-Escobar, A. F., Giraldo-Forero, A. F., Castro-Ospina, A.E., Jaramillo-Garzón, J. A. (2017). Efficient hyperparameter optimizationin convolutional neural networks by learning curves prediction. In CIARP 2017 (pp.143–151).

  41. Defferrard, M., Bresson, X., Vandergheynst, P. (2016). Convolutional neural networks on graphs with fast localized spectral fifiltering. In Proceedings of the neural information processing systems (pp. 3844–3852).

  42. Kipf, T. N., & Welling, M. (2016). Semi-supervised classifification with graph convolutional networks. arXiv:1609.02907.

  43. Bruna, J., Zaremba, W., & Szlam, A., & Lecun, Y. (2013). Spectral networks and locally connected networks on graphs. arXiv:1312.6203.

  44. Ma, Y., Ren, H., Khailany, B., Sikka, H., Luo, L., Natarajan, K., & Yu, B. (2019) High performance graph convolutional networks with applications in testability analysis. In ACM/IEEE Design Automation Conference (DAC) (pp. 18:1–18:6), Las Vegas, NV, June 2–6.

  45. Forecasting road traffic speeds by considering area-wide spatiotemporal dependencies based on a graph convolutional neural network (GCN),2019 Chinese Control Conference (CCC), 2019.

  46. Wu, C., Chai, L., Yang, J., Sheng, Y. Facial expression recognition using convolutional neural network on graphs

  47. Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv:1409.1259.

  48. Chung, J., Gulcehre, C., Cho, K. H., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555.

Download references

Acknowledgements

This work is partly supported by Xuzhou Science and Technology Plan Project (Grant No. KC19003) and Jiangsu major natural science research project of College and University (No. 19KJA470002).

Author information

Authors and Affiliations

  1. Jiangsu Province Key Laboratory of Intelligent Industry Control Technology, Xuzhou University of Technology, Xuzhou, 221018, China

    Lei Chen, Lulu Bei, Yuan An, Kailiang Zhang & Ping Cui

Authors
  1. Lei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lulu Bei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuan An
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kailiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ping Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lulu Bei.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, L., Bei, L., An, Y. et al. A Hyperparameters automatic optimization method of time graph convolution network model for traffic prediction. Wireless Netw 27, 4411–4419 (2021). https://doi.org/10.1007/s11276-021-02672-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11276-021-02672-5

Keywords

Search

Navigation